相关论文: MatAnyone: Stable Video Matting with Consistent Me…
Modern multi-object tracking (MOT) systems usually model the trajectories by associating per-frame detections. However, when camera motion, fast motion, and occlusion challenges occur, it is difficult to ensure long-range tracking or even…
Video object insertion requires ensuring spatio-temporal coherence and interactive realism, extending far beyond simple content placement. However, current approaches are often hindered by a reliance on explicit motion engineering or…
Image fusion seeks to seamlessly integrate foreground objects with background scenes, producing realistic and harmonious fused images. Unlike existing methods that directly insert objects into the background, adaptive and interactive fusion…
Video anomaly detection has gained significant attention due to the increasing requirements of automatic monitoring for surveillance videos. Especially, the prediction based approach is one of the most studied methods to detect anomalies by…
Video frame interpolation aims to synthesize realistic intermediate frames between given endpoints while adhering to specific motion semantics. While recent generative models have improved visual fidelity, they predominantly operate in a…
As foundation models become more popular, there is a growing need to efficiently finetune them for downstream tasks. Although numerous adaptation methods have been proposed, they are designed to be efficient only in terms of how many…
Autoregressive video diffusion models have proved effective for world modeling and interactive scene generation, with Minecraft gameplay as a representative application. To faithfully simulate play, a model must generate natural content…
Spatially consistent long-horizon video generation aims to maintain temporal and spatial consistency along predefined camera trajectories. Existing methods mostly entangle memory modeling with video generation, leading to inconsistent…
Stereo matching provides depth estimation from binocular images for downstream applications. These applications mostly take video streams as input and require temporally consistent depth maps. However, existing methods mainly focus on the…
Temporal grounding aims to localize a video moment which is semantically aligned with a given natural language query. Existing methods typically apply a detection or regression pipeline on the fused representation with the research focus on…
Generating temporally coherent high fidelity video is an important milestone in generative modeling research. We make progress towards this milestone by proposing a diffusion model for video generation that shows very promising initial…
Existing video stabilization methods often generate visible distortion or require aggressive cropping of frame boundaries, resulting in smaller field of views. In this work, we present a frame synthesis algorithm to achieve full-frame video…
We introduce region-specific image refinement as a dedicated problem setting: given an input image and a user-specified region (e.g., a scribble mask or a bounding box), the goal is to restore fine-grained details while keeping all…
Video Virtual Try-On (VVT) aims to synthesize garments that appear natural across consecutive video frames, capturing both their dynamics and interactions with human motion. Despite recent progress, existing VVT methods still suffer from…
Video mirror detection has received significant research attention, yet existing methods suffer from limited performance and robustness. These approaches often over-rely on single, unreliable dynamic features, and are typically built on…
Recently, transformer-based approaches have shown promising results for semi-supervised video object segmentation. However, these approaches typically struggle on long videos due to increased GPU memory demands, as they frequently expand…
Pose-guided human image animation aims to synthesize realistic videos of a reference character driven by a sequence of poses. While diffusion-based methods have achieved remarkable success, most existing approaches are limited to…
We introduce MapAnything, a unified transformer-based feed-forward model that ingests one or more images along with optional geometric inputs such as camera intrinsics, poses, depth, or partial reconstructions, and then directly regresses…
Match-cuts are powerful cinematic tools that create seamless transitions between scenes, delivering strong visual and metaphorical connections. However, crafting match-cuts is a challenging, resource-intensive process requiring deliberate…
We propose a novel feed-forward network for video inpainting. We use a set of sampled video frames as the reference to take visible contents to fill the hole of a target frame. Our video inpainting network consists of two stages. The first…